Update app.py

app.py

@@ -36,31 +36,6 @@ llm_generate = llama_cpp.Llama.from_pretrained(
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
-# Initialize Llama model
-"""
-try:
-    llm = Llama.from_pretrained(
-    repo_id="Qwen/Qwen1.5-0.5B-Chat-GGUF",
-    filename="*q4_0.gguf",
-    verbose=False,
-        n_ctx=4096,
-        n_threads=4,
-        n_gpu_layers=0,
-)
-    
-    llm = Llama(
-        model_path=MODEL_PATH,
-        chat_format="llama-2",
-        n_ctx=4096,
-        n_threads=8,
-        n_gpu_layers=0,
-    )
-    
-except Exception as e:
-    logger.error(f"Failed to load model: {e}")
-    raise
-"""
-
 app = fastapi.FastAPI(
     title="OpenGenAI",
     description="Your Excellect AI Physician")
@@ -105,6 +80,7 @@ async def chat(gen:GenModel):
         et = time()
         output["time"] = et - st
         messages.append({'role': "assistant", "content": output['choices'][0]['message']})
+        print(messages)
         return output
     except Exception as e:
         logger.error(f"Error in /complete endpoint: {e}")